• 물과 미래
• /
• 제29권4호
• /
• pp.109-118
• /
• 1996

신경망이론은 분산기억성질과 병렬국소처리를 수행하는 뇌의 활동을 이론화한 수학모형이다. 이러한 신경망이론의 장점은 분류문제, 대규모로 결합된 최적화문제, 비선형 사상문제 등에서 잘 나타나므로, 이 점을 이용하여 복잡한 강우의 예측을 시도하였다. 신경망이론을 적용하기 위해서 연속적인 값으로 표시되는 입력자료와 출력자료를 학습한 후 강우예측을 시행할 수 있는 다층신경망 모형을 구성하였다. 신경망이론에 의한 강우예측은 서울지역과 소양강유역의 1 시간 대위 강우자료에 적용하였다. 그 결과는 대체로 만족할 만하였다. 따라서 신경망이론은 양질의 자료가 충분히 확보될 경우복잡한 강우현상을 잘 예측할 것으로 기대된다.

• 상하수도학회지
• /
• 제28권3호
• /
• pp.277-286
• /
• 2014

Water discolouration and increased turbidity in the local water service distribution network occurred from hydraulic incidents such as drastic changes of flow and pressure at large consumer. Hydraulic incidents impose extra shear stresses on sediment layers in the network, leading to particle resuspension. Therefore, real time measuring instruments were installed for monitoring the variation of water flow, pressure, turbidity and particulates on a hydrant in front of the inlet point of large apartment complex. In this study, it is attempted to establish a more stable water supply plan and to reduce complaints from customers about water quality in a district metering area. To reduce red or black water, the water flow monitoring and control systems are desperately needed in the point of the larger consumers.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.153-155
• /
• 2006

An automatic remote water measurement system was developed. This system sends automatic remote measured and collected water meters data automatically from the transmitter with CDMA modem through SK-Telecom network The water meter data are received through LAH TCP/IP and displayed as test file on IE(Internet Explorer) window. The existing water meters of mechanical type have so many problems to measure data. The person must visit the location of each water meters and write down the data records manually. In this system the RF module has attached each water meter Client/Server programs are developed by network socket programming.

• 한국수자원학회논문집
• /
• 제51권11호
• /
• pp.959-969
• /
• 2018

노후화된 상수관로는 단수유발, 수압부족 및 수질악화, 싱크홀 발생 피해와 누수로 인한 경제적 손실 등을 초래한다. 하지만 모든 노후관로를 일시에 보수 및 교체하는 것은 불가능하므로, 사용 중인 관로의 노후도를 정량적으로 판단하여 상수관로의 개량 우선순위를 결정해야 한다. 본 연구에서는 ANN(Artificial Neural Network)-Clustering 기법이 상수관로의 노후도 평가를 위한 새로운 평가방법이 될 수 있음을 제시하였다. 본 연구는 전라남도 YG지역의 배수관로를 적용대상으로 진행하였으며, 관망성능평가 항목을 이용하여 전체 관로를 세 개의 등급으로 분류하여 노후도를 평가하였다. 또한, 본 연구의 적용 가능성을 판단하기 위하여 실무에서 적용 중인 점수평가법 결과와 비교분석을 실시하였으며, 전체 대상관로의 노후도 정도를 직관적으로 파악할 수 있도록 산정된 노후도 등급을 관망도에 도시하였다. 본 연구에서 제안한 노후관로 평가기법은 관로의 다양한 특성값을 손쉽게 변경하여 적용할 수 있으며, 점수평가법과 더불어 상수관로의 유지관리를 위한 객관적이고 합리적인 관망성능평가법이 될 수 있을 것으로 기대한다.

• 한국농공학회논문집
• /
• 제61권1호
• /
• pp.107-120
• /
• 2019

Reservoir water level data identify the current water storage of the reservoir, and they are utilized as primary data for management and research of agricultural water. For the reservoir storage management, Korea Rural Community Corporation (KRC) installed water level stations at around 1,600 agricultural reservoirs and has been collecting the water level data every 10 minutes. However, various kinds of outliers due to noise and erroneous problems are frequently appearing because of environmental and physical causes. Therefore, it is necessary to detect outlier and improve the quality of reservoir water level data to utilize the water level data in purpose. This study was conducted to detect and classify outlier and normal data using two different models including the threshold model and the artificial neural network (ANN) model. The results were compared to evaluate the performance of the models. The threshold model identifies the outlier by setting the upper/lower bound of water level data and variation data and by setting bandwidth of water level data as a threshold of regarding erroneous water level. The ANN model was trained with prepared training dataset as normal data (T) and outlier (F), and the ANN model operated for identifying the outlier. The models are evaluated with reference data which were collected reservoir water level data in daily by KRC. The outlier detection performance of the threshold model was better than the ANN model, but ANN model showed better detection performance for not classifying normal data as outlier.

• 한국세라믹학회지
• /
• 제44권3호
• /
• pp.162-168
• /
• 2007

Silica wet gels were prepared ken water glass ($29\;wt%\;SiO_{2}$) by using Amberlite as a ion exchange resin. After washing in distilled water, the wet gels were further aged in a solution of TEOS/EtOH to strengthen of 3-dimensional network structure. As increase TEOS content in aging solution, BET surface area and porosity of the ambient dried silica aerogels were significantly decreased, and average pore diameter was also decreased 30 nm to -10 nm. Also, higher density and compressive strength were obtained in case of higher TEOS content. This is due to precipitation of $SiO_{2}$ nano particles by TEOS. Hence, TEOS addition plays an important role of both strengthening and stiffness of silica wet gel network. By adding over 30 vol% TEOS, a crack-free monolithic silica aerogel tiles were obtained and its density, compressive strength, and thermal conductivity were shown $0.232g/cm^{3}$, 7.3 MPa, and 0.029 W/mk, respectivly.

• 한국농공학회논문집
• /
• 제59권3호
• /
• pp.97-110
• /
• 2017

This study investigates the efficiencies of machine learning models, including artificial neural network (ANN), generalized regression neural network (GRNN), adaptive neuro-fuzzy inference system (ANFIS) and random forest (RF), for reservoir water level forecasting in the Chungju Dam, South Korea. The models' efficiencies are assessed based on model efficiency indices and graphical comparison. The forecasting results of the models are dependent on lead times and the combination of input variables. For lead time t = 1 day, ANFIS1 and ANN6 models yield superior forecasting results to RF6 and GRNN6 models. For lead time t = 5 days, ANN1 and RF6 models produce better forecasting results than ANFIS1 and GRNN3 models. For lead time t = 10 days, ANN3 and RF1 models perform better than ANFIS3 and GRNN3 models. It is found that ANN model yields the best performance for all lead times, in terms of model efficiency and graphical comparison. These results indicate that the optimal combination of input variables and forecasting models depending on lead times should be applied in reservoir water level forecasting, instead of the single combination of input variables and forecasting models for all lead times.

• 센서학회지
• /
• 제21권1호
• /
• pp.46-52
• /
• 2012

The rapid water pollution in stream, river, lake and sea in recent years raises an urgent need for continuous monitoring and policymaking to conserve the global clean environment. In particular, the increasing water pollution in coastal marine areas adds to the importance of the environmental monitoring systems. In this paper, the mobile server is designed to gathers information of the water quality at coastal areas. The obtained data by the server is transmitted from field servers to the base station via multi-hop communication in wireless sensor network. The information collected includes dissolved oxygen(DO), hydrogen ion exponent(pH), temperature, etc. By the information provided the real-time monitoring of water quality at the coastal marine area. In addition, wireless sensor network-based flooding routing protocol was designed and used to transfer the measured water quality information efficiently. Telosb sensor node is programmed using nesC language in TinyOS platform for small scale wireless sensor network monitoring from a remote server.

• 한국환경과학회지
• /
• 제31권1호
• /
• pp.33-42
• /
• 2022

The objective of this study is to determine the appropriate size of the inlet pipe diameter and thereby conduct hydraulic analysis for the Korean water distribution network. To this end, the data tables for equivalent pipe diameters and outflow rates presently employed in Korea were adopted. By incorporating the table of equivalent pipe diameters, it was found that the size of the inlet pipe diameter was overestimated, which can cause shortage of water pressure and malfunctioning or insufficiency of outflow rate in the corresponding adjacent region. However, by conducting hydraulic analysis based on the table of outflow rates, relatively reasonable flow rates were observed. Furthermore, by comparing the real demand-driven analysis (RDDA) approach and demand-driven analysis (DDA) approach toward managing the huge water demand, it was observed that DDA could not effectively respond to real hourly usage conditions, whereas RDDA (which reflects the hourly effects of inlet pipe diameter and storage tanks) demonstrated results similar to that of real water supply.

• 한국수자원학회논문집
• /
• 제40권4호
• /
• pp.325-334
• /
• 2007

본 연구에서는 점진적인 유량 및 압력이 변화하는 상수관망에서 Rigid Water Column Theory를 이용하여 정상모형의 확장기간 모의해석보다 정확하고 수충격 해석보다는 계산비용 및 노력 측면에서 효율적으로 장시간 부정류 해석 모형을 개발하였다. 개발된 모형을 이용하여 실제관망에 대하여 24 시간 열 수요량을 고려한 부정류 해석 및 밸브폐쇄로 인한 수충격해석 모의에 적용하였고 해석 결과는 다음과 같다. 24 시간 일변화 모의의 경우에 수요량이 증가할 경우 모든 관로에서 압력감소가 나타났으며 수요량이 감소할 경우 압력증가가 나타났다. 그리고 일 수요량의 변화에 따라 나타난 절점에서의 유량 및 압력 변화폭은 각 절점마다 다르고 수요량과 유량의 변화양상이 반대로 나타나는 관로도 발생하고 있으며 KYPIPE2의 결과와 본 모형의 유량 및 압력차이도 발생하고 있어 상수관망의 동역학적 해석의 필요성이 대두되었다. 밸브폐쇄로 인한 수충격모의에 본 모형이 적용되었을 때 본 모형은 유체의 압축성을 무시함으로 인해 밸브 완전 폐쇄와 동시에 압력과 유량의 변화가 전 관망에 발생하였고 수충격모형은 유체의 탄성으로 인해 발생된 압력파의 도달시간이 필요함으로 압력과 유량변화가 지체되어 나타났으나 전체적인 변화양상 및 변화폭의 크기 등은 유사한 경향을 나타내어 본 모형의 적용성을 입증하였다. 본 연구에서 개발된 프로그램은 장기간 점진적인 관로 부정류를 비교적 정확하게 해석할 수 있을 것으로 판단되며 이를 이용하여 관로내 오염물의 확산해석, 수요량을 고려한 절점에서의 압력제어 및 누수저감, 장기간 관로내의 유량 및 압력 변화를 고려한 관망관리 등의 분야에서 효율적으로 이용될 수 있을 것으로 기대되었다.